Calculate your monthly cost
| Model | Per request | Per day | Per month | Chat plan instead |
|---|
Custom model: adds a row to the table.
How the cost is calculated
Each request costs input tokens ÷ 1,000,000 × input price + output tokens ÷ 1,000,000 × output price. A typical chat message is around 100 to 300 tokens, a page of text around 700, and a long document tens of thousands. Not sure how many tokens you have? Use the token counter.
The last column shows the chat plan that includes the model in AimiChat. If your monthly API cost is higher than the plan price and you are the only user, the plan is the cheaper way in.
Frequently asked questions
How is the AI API cost calculated?
Cost per request is input tokens divided by one million times the input price, plus output tokens divided by one million times the output price. The calculator multiplies that by your requests per day and the days in the month.
Why are output tokens priced higher than input tokens?
Providers charge more for generated tokens than for tokens you send, usually by a factor of four to five. Reply length therefore moves the bill more than prompt length does.
Is the API cheaper than a chat subscription?
For light use, a subscription is usually cheaper and simpler. API pricing wins when you run automated, high-volume or product workloads. The calculator shows both so you can compare your own numbers.
Where do these prices come from?
Prices come from the model makers' published API pricing and were checked on September 24, 2026. They can change, so confirm on the provider's pricing page before you commit to a budget.